2 papers
cs.CV2025
MLVTG: Mamba-Based Feature Alignment and LLM-Driven Purification for Multi-Modal Video Temporal Grounding
Zhiyi Zhu, Xiaoyu Wu, Zihao Liu +1
Video Temporal Grounding (VTG), which aims to localize video clips corresponding to natural language queries, is a fundamental yet challenging task in video understanding. Existing…
cs.CV2025
Rethinking Metrics and Benchmarks of Video Anomaly Detection
Zihao Liu, Xiaoyu Wu, Wenna Li +2
Video Anomaly Detection (VAD), which aims to detect anomalies that deviate from expectation, has attracted increasing attention in recent years. Existing advancements in VAD primar…